Search Results for "wise memory optimizer"
Sort By:
Showing 36 open source projects for "wise memory optimizer"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
1
MSA: Memory Sparse Attention
Trainable latent-memory framework for 100M-token contexts
MSA, or Memory Sparse Attention, is a research framework for scaling language-model memory to extremely long contexts. It replaces full attention over all tokens with sparse selection of compressed latent memory states. Document-wise rotary position encoding and top-k routing keep training and inference close to linear complexity. A tiered KV-cache design stores routing keys on GPU while larger content states can remain on CPU. -
2
NVIDIA Model Optimizer
A unified library of SOTA model optimization techniques
Model Optimizer is a unified library that provides state-of-the-art techniques for compressing and optimizing deep learning models to improve inference efficiency and deployment performance. It brings together multiple optimization strategies such as quantization, pruning, distillation, and speculative decoding into a single cohesive framework. The library is designed to reduce model size and computational requirements while maintaining accuracy, making it particularly valuable for deploying... -
3
AirLLM
AirLLM 70B inference with single 4GB GPU
AirLLM is an open source Python library that enables extremely large language models to run on consumer hardware with very limited GPU memory. The project addresses one of the main barriers to local LLM experimentation by introducing a memory-efficient inference technique that loads model layers sequentially rather than storing the entire model in GPU memory. This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of VRAM. ... -
4
Model Explorer
A modern model graph visualizer and debugger
Model Explorer is a visual tool for exploring, debugging, and optimizing ML models deployed on edge devices. Developed by Google AI Edge, it offers a browser-based interface to inspect layer-wise performance, memory usage, and inference timing of TensorFlow Lite and other supported models. It’s a powerful utility for developers optimizing models for constrained environments. -
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
Roblox Ping Optimizer
Roblox Ping Optimizer ping, safe & clean, no exploits. Enhance!
🚀 Roblox Ping Optimizer- Created by Akash Siddique! 🎮 🔥 Fresh Update: Sleek New Modern UI! ⚡ Boost Your Gameplay Experience! Elevate your Roblox sessions with ultra-fast responses and optimized performance. Conquer the virtual world smoother and faster than ever. Join the revolution and take your gaming to the next level! 🌟 Why Choose Roblox Ping Booster? Unleash your gaming potential with just one click! 🚀 -
6
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
...The project combines technical notes, code examples, and practical experiments that demonstrate how common computational kernels can be optimized to improve speed and memory efficiency. Instead of presenting only theoretical explanations, the repository includes hand-written CUDA implementations of fundamental operations such as reductions, element-wise computations, softmax, and attention mechanisms. These examples show how different optimization techniques influence performance on modern GPU hardware and allow readers to experiment with real implementations. ... -
7
InMemoryDatasets.jl
Multithreaded package for working with tabular data in Julia
InMemoryDatasets.jl is a multithreaded package for data manipulation and is designed for Julia 1.6+ (64-bit OS). The core computation engine of the package is a set of customized algorithms developed specifically for columnar tables. -
8
FSRS4Anki
A modern Anki custom scheduling based on Free Spaced Repetition
A modern spaced-repetition scheduler for Anki based on the Free Spaced Repetition Scheduler algorithm. -
9
Polars
Dataframes powered by a multithreaded, vectorized query engine
Polars is a high-performance, multi-language DataFrame library built in Rust using Apache Arrow. It delivers blazing-fast, vectorized, and parallel data manipulation with both eager and lazy execution, making it an excellent tool for data processing in Python, Rust, Node.js, R, and SQL contexts. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
10
PhoneNumberKit
A Swift framework for parsing and formatting phone numbers
...All of your interactions with PhoneNumberKit happen through a PhoneNumberKit object. The first step you should take is to allocate one. A PhoneNumberKit instance is relatively expensive to allocate (it parses the metadata and keeps it in memory for the object's lifecycle), you should try and make sure PhoneNumberKit is allocated once and deallocated when no longer needed. To parse a string, use the parse function. The region code is automatically computed but can be overridden if needed. PhoneNumberKit automatically does a hard type validation to ensure that the object created is valid, this can be quite costly performance-wise and can be turned off if needed. -
11
LightGBM
Gradient boosting framework based on decision tree algorithms
LightGBM or Light Gradient Boosting Machine is a high-performance, open source gradient boosting framework based on decision tree algorithms. Compared to other boosting frameworks, LightGBM offers several advantages in terms of speed, efficiency and accuracy. Parallel experiments have shown that LightGBM can attain linear speed-up through multiple machines for training in specific settings, all while consuming less memory. LightGBM supports parallel and GPU learning, and can handle... -
12
rtabmap
RTAB-Map library and standalone application
...The loop closure detector uses a bag-of-words approach to determine how likely a new image comes from a previous location or a new location. When a loop closure hypothesis is accepted, a new constraint is added to the map’s graph, then a graph optimizer minimizes the errors in the map. A memory management approach is used to limit the number of locations used for loop closure detection and graph optimization so that real-time constraints on large-scale environments are always respected. RTAB-Map can be used alone with a handheld Kinect, a stereo camera or a 3D lidar for 6DoF mapping, or on a robot equipped with a laser rangefinder for 3DoF mapping. -
13
verl-agent
Designed for training LLM/VLM agents via RL
...The framework supports multi-turn interactions between agents and their environments, allowing the system to receive feedback after each step and adjust its strategy accordingly. This step-wise interaction model makes it possible to train agents to operate in long-horizon scenarios where decisions depend on cumulative context and previous outcomes. Developers can configure memory modules that determine how historical information is stored and incorporated into each step of the reasoning process. -
14
This script is a system tuning script for Linux (especially aimed at EasyOS / Puppy Linux) that tries to make the machine feel faster, more responsive, and more SSD-friendly by changing a number of kernel and runtime settings. Here is the explanation in English: What this script does The script creates a small log file in: /tmp/pp4mnk-blackfire.log Then it waits 4 seconds and starts applying a series of performance tweaks in these areas: • Memory • CPU • SSD / disk...
-
15
FPS Booster
Optimizer FPS boosts performance for Roblox, CS reducing ping ,memory
Optimizer FPS,Fps Booster is a lightweight tool 🎮 that boosts your system’s performance for popular games like Roblox, CS, and Valorant. It’s particularly effective for Roblox, where it helps to reduce ping 🌐 and improve overall gameplay 🚀. Even if you’re using a low-end PC, Optimizer FPS can enhance your gaming experience by optimizing settings and providing smoother, more responsive gameplay. Here’s a detailed look at what it can do: -
16
TensorRT
C++ library for high performance inference on NVIDIA GPUs
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers,... -
17
rw
rw calculates rank-width and rank-decompositions.
...It is based on ideas from "Computing rank-width exactly" by Sang-il Oum, "Sopra una formula numerica" by Ernesto Pascal, "Generation of a Vector from the Lexicographical Index" by B.P. Buckles and M. Lybanon and "Fast additions on masked integers" by Michael D. Adams and David S. Wise. On 2009's computers it works quite well up to graph sizes of about 28 nodes. Runtime and memory usage are exponential in the graph size. -
18
Multron Win Cleaner
A Community driven database based Windows Disk Cleaner With Utilities
...Security Check: finds insecure Windows settings and fixes them with one-click undo. System Health: DISM and SFC with clear result panels. Tools: Duplicate and Large File Finders, Memory Cleaner, Startup Manager, firewall rule cleaner, shortcut fixer, locked file unlock and boot operations. Also: 12 languages, dark/light themes, built-in updates, installer and portable versions. Users can request new features. -
19
ProPainter
Improving Propagation and Transformer for Video Inpainting
...It is designed to remove objects, complete missing regions, and fill masked areas in videos while preserving temporal consistency. The project accepts video input or split frames along with frame-wise masks that define the areas to reconstruct. It provides pretrained models, example inputs, inference scripts, and an interactive demo workflow for object removal. The repository also includes memory-efficient inference features to reduce GPU out-of-memory issues during video processing. ProPainter is useful for research, video editing experiments, object removal prototypes, and completion tasks where consistent motion is important. -
20
rathole
A lightweight and high-performance reverse proxy for NAT traversal
...High Performance Much higher throughput can be achieved than frp, and more stable when handling a large volume of connections. Low Resource Consumption Consumes much fewer memory than similar tools. See Benchmark. The binary can be as small as ~500KiB to fit the constraints of devices, like embedded devices as routers. Security Tokens of services are mandatory and service-wise. The server and clients are responsible for their own configs. With the optional Noise Protocol, encryption can be configured at ease. ... -
21
FairScale
PyTorch extensions for high performance and large scale training
FairScale is a collection of PyTorch performance and scaling primitives that pioneered many of the ideas now used for large-model training. It introduced Fully Sharded Data Parallel (FSDP) style techniques that shard model parameters, gradients, and optimizer states across ranks to fit bigger models into the same memory budget. The library also provides pipeline parallelism, activation checkpointing, mixed precision, optimizer state sharding (OSS), and auto-wrapping policies that reduce boilerplate in complex distributed setups. Its components are modular, so teams can adopt just the sharding optimizer or the pipeline engine without rewriting their training loop. ... -
22
V8 Perf
Notes and resources related to v8 and thus Node.js performance
...It explains how V8 represents JavaScript data internally and how those representations can influence execution speed. Compiler documentation explores the Ignition interpreter, TurboFan optimizer, optimization decisions, and deoptimization behavior. Memory sections explain heap organization, garbage collection, object references, allocations, and leak investigation. Profiling material covers inspection tools, runtime flags, performance analysis, and flamegraph generation. Additional notes examine snapshots, code caching, runtime functions, and JavaScript language features from a performance perspective. ... -
23
Fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python
Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks. We provide reference implementations of various sequence modeling papers. Recent work by Microsoft and Google has shown that data parallel training can be made significantly more efficient by sharding the model parameters and optimizer state across data parallel workers. These ideas are encapsulated in the... -
24
Img Optimizer Gradle Plugin
Gradle plugin for optimizing PNGs
...Because it is integrated into the build, it can process only changed images and skip redundant work, improving performance. Its configuration is minimal, making it easy to adopt in existing Android projects. For apps sensitive to download size or memory usage, this plugin offers a practical way to squeeze out extra gains in deployment efficiency. -
25
SimSiam
PyTorch implementation of SimSiam
SimSiam is a PyTorch implementation of “Exploring Simple Siamese Representation Learning” by Xinlei Chen and Kaiming He. The project introduces a minimalist approach to self-supervised learning that avoids negative pairs, momentum encoders, or large memory banks—key complexities of prior contrastive methods. SimSiam learns image representations by maximizing similarity between two augmented views of the same image through a Siamese neural network with a stop-gradient operation, preventing...
